{"id":"https://openalex.org/W3207551191","doi":"https://doi.org/10.1109/icassp43922.2022.9747180","title":"MetricGAN-U: Unsupervised Speech Enhancement/ Dereverberation Based Only on Noisy/ Reverberated Speech","display_name":"MetricGAN-U: Unsupervised Speech Enhancement/ Dereverberation Based Only on Noisy/ Reverberated Speech","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207551191","doi":"https://doi.org/10.1109/icassp43922.2022.9747180","mag":"3207551191"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747180","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Szu-Wei Fu","raw_affiliation_strings":["Academia Sinica,Research Center for Information Technology Innovation,Taipei,Taiwan","Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Research Center for Information Technology Innovation,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058798840","display_name":"Cheng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng Yu","raw_affiliation_strings":["Academia Sinica,Research Center for Information Technology Innovation,Taipei,Taiwan","Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Research Center for Information Technology Innovation,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071855826","display_name":"Kuo-Hsuan Hung","orcid":"https://orcid.org/0009-0007-0974-4873"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuo-Hsuan Hung","raw_affiliation_strings":["Academia Sinica,Research Center for Information Technology Innovation,Taipei,Taiwan","Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Research Center for Information Technology Innovation,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040811098","display_name":"Mirco Ravanelli","orcid":"https://orcid.org/0000-0002-3929-5526"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mirco Ravanelli","raw_affiliation_strings":["Mila-Quebec AI Institute,Montreal,Canada","Mila-Quebec AI Institute, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Mila-Quebec AI Institute,Montreal,Canada","institution_ids":["https://openalex.org/I4210164802"]},{"raw_affiliation_string":"Mila-Quebec AI Institute, Montreal, Canada","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica,Research Center for Information Technology Innovation,Taipei,Taiwan","Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Research Center for Information Technology Innovation,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071471469"],"corresponding_institution_ids":["https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":4.9145,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.96505038,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7412","last_page":"7416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7990531921386719},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.7745420932769775},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7162490487098694},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6774617433547974},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6047951579093933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.514518678188324},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4738919138908386},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.44190678000450134},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.42616021633148193},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18840038776397705},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08215263485908508},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07119014859199524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990531921386719},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.7745420932769775},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7162490487098694},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6774617433547974},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6047951579093933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.514518678188324},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4738919138908386},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.44190678000450134},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.42616021633148193},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18840038776397705},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08215263485908508},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07119014859199524},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747180","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W1582774210","https://openalex.org/W1897240248","https://openalex.org/W2078528584","https://openalex.org/W2099471712","https://openalex.org/W2105854852","https://openalex.org/W2121973264","https://openalex.org/W2125114513","https://openalex.org/W2164502538","https://openalex.org/W2603567530","https://openalex.org/W2891433113","https://openalex.org/W2897371647","https://openalex.org/W2943895317","https://openalex.org/W2949558265","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W3014986435","https://openalex.org/W3015806165","https://openalex.org/W3025844872","https://openalex.org/W3031135612","https://openalex.org/W3096643087","https://openalex.org/W3096949857","https://openalex.org/W3097627357","https://openalex.org/W3122264812","https://openalex.org/W3147539069","https://openalex.org/W3149225678","https://openalex.org/W3161480375","https://openalex.org/W3167533889","https://openalex.org/W3174264304","https://openalex.org/W3178513759","https://openalex.org/W3186301694","https://openalex.org/W3197912330","https://openalex.org/W3198130028","https://openalex.org/W4225302959","https://openalex.org/W4226339160","https://openalex.org/W4253928870","https://openalex.org/W4254751698","https://openalex.org/W4320013936","https://openalex.org/W6755675054","https://openalex.org/W6762114000","https://openalex.org/W6785764544","https://openalex.org/W6797236388","https://openalex.org/W6798972960","https://openalex.org/W6810523761"],"related_works":["https://openalex.org/W4220926404","https://openalex.org/W3123344745","https://openalex.org/W2022538999","https://openalex.org/W1955763106","https://openalex.org/W2002243964","https://openalex.org/W3090086172","https://openalex.org/W3171883019","https://openalex.org/W1585241115","https://openalex.org/W2120213246","https://openalex.org/W1564179349"],"abstract_inverted_index":{"Most":[0],"of":[1,18],"the":[2,40,53,79,94],"deep":[3],"learning-based":[4],"speech":[5,22,60,89,99],"enhancement":[6],"models":[7],"are":[8,23],"learned":[9],"in":[10,32,66,110],"a":[11],"supervised":[12],"manner,":[13],"which":[14,72],"implies":[15],"that":[16,106],"pairs":[17],"noisy":[19,29,88],"and":[20,113],"clean":[21,59],"required":[24,91],"during":[25],"training.":[26,64],"Consequently,":[27],"several":[28],"speeches":[30],"recorded":[31],"daily":[33],"life":[34],"cannot":[35],"be":[36],"used":[37],"to":[38,51,76,92],"train":[39,93],"model.":[41],"Although":[42],"certain":[43],"unsupervised":[44,83],"learning":[45],"frameworks":[46],"have":[47],"also":[48],"been":[49],"proposed":[50],"solve":[52],"\"pair\"":[54],"constraint,":[55],"they":[56],"still":[57],"require":[58],"or":[61],"noise":[62],"for":[63,74],"Therefore,":[65],"this":[67],"paper,":[68],"we":[69],"propose":[70],"MetricGAN-U,":[71,86],"stands":[73],"MetricGANunsupervised,":[75],"further":[77],"release":[78],"constraint":[80],"from":[81],"conventional":[82],"learning.":[84],"In":[85],"only":[87],"is":[90],"model":[95],"by":[96],"optimizing":[97],"non-intrusive":[98],"quality":[100],"metrics.":[101,115],"The":[102],"experimental":[103],"results":[104],"verified":[105],"MetricGAN-U":[107],"outperforms":[108],"baselines":[109],"both":[111],"objective":[112],"subjective":[114]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-01T06:05:34.837733","created_date":"2025-10-10T00:00:00"}